Yutai Zhou

yutaizho at usc.edu

Hello! I am a 4th year Computer Science Ph.D. student at USC, where I am fortunate to be co-advised by Erdem Bıyık and Stephen Tu. My research is centered on RL from preference feedback, representation learning, and offline policy evaluation. I am currently collaborating with Toyota Research Institute.

Prior to starting my Ph.D., I was a research engineer at MIT Lincoln Laboratory for 3.5 years, where I collaborated closely with Mykel Kochenderfer and completed graduate coursework from Stanford Online while working full time. Even before that, I received my B.S. in Computer Science from the University of Florida, where I worked with Alina Zare.

Fun fact: My name is pronounced "you-tie", but it is frequently mispronounced as "you-tee" or "Utah". I have even gotten "Tyler" once!

CV  /  GitHub  /  Twitter  /  LinkedIn  /  Google Scholar

Yutai Zhou
Education
News
Publications (Highlighted / All)

(* denotes equal contribution)

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
Anthony Liang*, Pavel Czempin*, Matthew Hong, Yutai Zhou, Erdem Bıyık, and Stephen Tu
IROS 2026.
[website] [paper] [code]
AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations
Litian Gong, Fatemeh Bahrani, Yutai Zhou, Amin Banayeeanzade, Jiachen Li, and Erdem Bıyık
ICRA 2026.
[website] [paper] [code]
GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning
Amin Banayeeanzade*, Fatemeh Bahrani*, Yutai Zhou, and Erdem Bıyık
IROS 2025.
[website] [paper] [code]
In Pursuit of Predictive Models of Human Preferences Toward AI Teammates
Ho Chit Siu, Jaime D. Peña, Yutai Zhou, and Ross E. Allen
arXiv preprint, 2025.
[paper]
In-Context Generalization to New Tasks From Unlabeled Observation Data
Anthony Liang, Pavel Czempin, Yutai Zhou, Stephen Tu, and Erdem Bıyık
ICML 2024 Workshop on In-Context Learning.
[paper]
Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning
Sheng Li, Yutai Zhou, Ross Allen, and Mykel J. Kochenderfer
ICRA 2022.
[paper]
Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi
Ho Chit Siu, Jaime D. Pena, Kimberlee C. Chang, Edenna Chen, Yutai Zhou, Victor J. Lopez, Kyle Palko, and Ross E. Allen
NeurIPS 2021.
[paper]
Health-Informed Policy Gradients for Multi-Agent Reinforcement Learning
Ross E. Allen, Jayesh K. Gupta, Jaime Pena, Yutai Zhou, Javona White Bear, and Mykel J. Kochenderfer
AAMAS 2021 Workshop on Optimization and Learning in Multiagent Systems.
[paper]
Towards a Distributed Framework for Multi-Agent Reinforcement Learning Research
Yutai Zhou, Shawn Manuel, Peter Morales, Sheng Li, Jaime Pena, and Ross E. Allen
HPEC 2020. Outstanding Paper Award.
[paper]
Service
Misc.

I spent much of my childhood in Shanghai, China, and much of my teenage / college years in Florida, USA. Outside of work, I love strength training and have competed in multiple powerlifting and strongman competitions. I just learned how to swim in 2025 (despite growing up in coastal cities all my life), and am now trying to learn salsa and bachata!



Last updated on July 31, 2026.
Inspired by this and that.